Skip to content

README.md

Latest commit

 

History

History
39 lines (34 loc) · 1.36 KB

README.md

File metadata and controls

39 lines (34 loc) · 1.36 KB
Raw

💬 Chat with Websites (OpenAI Version)

An end-to-end Retrieval-Augmented Generation (RAG) application that allows users to have interactive conversations with any website. By providing a URL, the application scrapes the content, indexes it, and allows for context-aware Q&A using OpenAI's powerful language models.

🚀 Features

  • URL-Based Chat: Enter any website URL to instantly start a conversation with its content.
  • Contextual Memory: Maintains chat history to provide accurate responses based on the full conversation flow.
  • RAG Pipeline: Utilizes LangChain for document loading, text splitting, and retrieval.
  • Vector Search: Uses Chroma DB and OpenAI Embeddings for high-performance semantic search.

🛠️ Tech Stack

  • Frontend: Streamlit
  • LLM: OpenAI GPT-4o-mini
  • Embeddings: OpenAI text-embedding-3-small
  • Orchestration: LangChain
  • Database: Chroma DB (Vector Store)

📋 Prerequisites

  • Python 3.9+
  • OpenAI API Key

⚙️ Setup

  1. Clone the repository: 
    git clone https://github.com/Anuroop128/chat-with-websites.git
cd chat-with-websites
  2. Install dependencies: 
    pip install -r requirements.txt
  3. Create a .env file and add your OpenAI API Key: 
    OPENAI_API_KEY=your_openai_api_key_here
  4. Run the app: 
    streamlit run src/app.py